检索结果-内蒙古大学图书馆

IEEE International Conference on Electrical, Computer, and Energy Technologies (ICECET)

作者： Hossain, Hasnain Bin Mahmud, Tahmid Rahman, A. K. M. Mahbubur Amin, M. Ashraful Ali, Amin Ahsan Independent Univ Bangladesh Artificial Intelligence & Cybernet Lab Dhaka Bangladesh

ISBN: (纸本)9781665442312

Feature selection is getting significant importance in the fields of machine learning specially for dealing with high dimensional datasets. Feature selection techniques such as swarm algorithms have proven to be very effective in extracting meaningful information from large amounts of high dimensional data, thus improving prediction performance and reducing computation time. In this research, we evaluate the effectiveness of introducing mRMR (minimum Redundancy-Maximum Relevance) as an information theoretic filtering criterion on top of swarm optimization algorithms to further improve on existing techniques. We also present a comparison of the performances of two recent swarm algorithms against the well-known Artificial Bee Colony algorithm after incorporating mRMR-based filtering to demonstrate the applicability of this technique.

关键词： swarm algorithm information theory feature selection

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Recent swarm algorithms for Continuous Optimization 5

Comparative Study of Recent Swarm Algorithms for Continuous ...

引用

5th International Conference on Computer Science and Computational Intelligence (ICCSCI)

作者： Indramaya, Ending Suyanto, Suyanto Telkom Univ Bandung 40257 Indonesia

Optimization is a problem of finding the best solution from various possible solutions. In solving optimization problems, collective intelligence algorithms are often used as a method for finding solutions to optimization problems. This is because collective intelligence has various algorithms to search for various types of continuous optimization problems. However, not all of these algorithms work with the same performance. An algorithm can work better for a problem than other algorithms. Therefore, the diversity of performance of this algorithm must be identified, analyzed, and compared. By knowing the strengths, weaknesses, nature, and behaviour of the algorithm in solving various problems, this is believed to be able to realize the use of more effective algorithms in solving various problems. In this paper, Dragonfly algorithm (DA), Grey Wolf algorithm (GWO), and Rao algorithms are carefully investigated using nine benchmark functions. The result indicates that Rao generally performed better than GWO and DA. DA is outperformed by GWO and Rao in reaching the convergence score, although DA has an edge in searching a large search space, and in theory, given enough population, DA can perform better than GWO or Rao. (C) 2021 The Authors. Published by Elsevier B.V.

关键词： Collective intelligence Comparison Continuous Optimization swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

AAMR-FCN myeloma cancer net: Adaptive and attention-based mask R-FCN for diagnosing myeloma cancer using cell microscopic images with hybrid heuristic strategy

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 100卷

作者： Shinu, M. M. Pamela, D. Devadhas, G. Glan Isaac, J. Samson Karunya Inst Technol & Sci Dept Biomed Engn Coimbatore 641114 Tamil Nadu India Adi Shankara Inst Engn & Technol Dept Elect & Biomed Engg Kalady Kerala India CMR Univ Bengaluru 562149 Karnataka India Karunya Inst Technol & Sci Dept Biomed Engn Coimbatore 641114 Tamil Nadu India

The core concept of this task is to detect multiple myeloma cancer by adopting microscopic blood data. Because of the microscopic blood data, the issues that occurred during the interclass visual similarity can be easily detected. The gathered images are segmented into more regions to detect the disease very effectively by newly developed Adaptive and Attention-based Mask R-FCN (AAMR-FCN), where the two networks such as Regions with Convolutional Neural Networks (R-CNN) and Fully Convolutional Network (FCN) is integrated to formulate the AAMR-FCN to provide detailed and precise segmentation of nucleus cell regions, which is crucial for accurate diagnosis and monitoring of the disease progression. The parameters present within the R-CNN and FCN are optimized with the assistance of the developed Hybridized Lemurs Optimizer with Chameleon swarm algorithm (HLO-CSA) for maximizing the performance of the segmentation process. The HLO-CSA algorithm allows for a quicker and more efficient analysis of medical images, ultimately leading to improved patient outcomes and a higher success rate in identifying and treating myeloma cancer. These segmentation results may help diagnose myeloma cancer from microscopic images. From the result validation, the dice coefficient of the developed HLOCSA-AAMR-FCN model is 0.998. Similarly, the existing techniques were secured as 0.984 of BWO-AAMR-FCN, 0.985 of AOA-AAMR-FCN, 0.987 of LOA-AAMR-FCN and 0.989 of CSA-AAMR-FCN. Thus, it is revealed that the developed model attains enriched results than the other baseline techniques. With a significant margin of improvement over the baseline methods the developed model showcases its effectiveness in accurately identifying and diagnosing myeloma cancer.

关键词： Multiple Myeloma Detection Microscopic Images Adaptive and Attention-based Mask Regions-Fully Convolutional Network Hybridized Lemurs Optimizer with Chameleon swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Recent swarm algorithms for Continuous Optimization

引用

Procedia Computer Science 2021年 179卷 685-695页

作者： Ending Indramaya Suyanto Suyanto Telkom University Bandung 40257 Indonesia

关键词： Collective intelligence Comparison Continuous Optimization swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

swarm approach based on gravity for optimizing energy savings in grid systems

引用

JOURNAL OF HEURISTICS 2014年第6期20卷 617-641页

作者： Arsuaga-Rios, Maria Vega-Rodriguez, Miguel A. CERN European Org Nucl Res Dept Informat Technol CH-1211 Geneva 23 Switzerland Univ Extremadura Escuela Politecn Dept Technol Comp & Commun ARCO Res Grp Caceres 10003 Spain

Execution time optimization is one of the most important objectives to accomplish for experiments launched on grid environments. However, the computing community is becoming more conscious about energy savings, seeking their optimization. In this work, both execution time and energy consumption are optimized through two swarm and multi-objective algorithms based on both physics and biology fields. On the one hand, multi-objective gravitational search algorithm (MOGSA) is inspired by the gravity forces between the planet masses. On the other hand, Multi-Objective Firefly algorithm is based on the light attraction between the fireflies. These swarm algorithms are compared with the standard multi-objective algorithm non-dominated sorting genetic algorithm II to study their efficiency as multi-objective algorithms. Moreover, the best algorithm proposed, MOGSA, is compared with MOHEFT (a multi-objective version of one of the most-used algorithms in workflow scheduling, HEFT), and also with two real grid schedulers: Workload Management System and deadline budget constraint. Results show the superior performance of MOGSA regarding the others.

关键词： swarm algorithm Multiobjective optimization Grid computing Scheduling

来源：评论

学校读者我要写书评

暂无评论

Methods for Improving the Efficiency of swarm Optimization algorithms. A Survey

引用

AUTOMATION AND REMOTE CONTROL 2021年第6期82卷 935-967页

作者： Hodashinsky, I. A. Tomsk State Univ Control Syst & Radioelect Tomsk 634050 Russia

swarm algorithms belong to the class of population metaheuristic optimization methods. Despite the use of various metaphors, most swarm algorithms have similar structures, where one can distinguish common components such as the decision population initialization, decision diversification, and decision intensification. Based on the concept of generality, an analysis of key approaches to, methods for, and ways of increasing the efficiency of swarm optimization algorithms was carried out. In the survey, swarm optimization algorithms are viewed as a set of operators without a detailed discussion of each algorithm. The main focus is on the analysis of the key components of the algorithms. The main idea behind efficiency improvement is to maintain a balance between diversification and intensification. In this context, we consider mechanisms for supporting population diversity, methods for tuning and adjusting the swarm algorithm parameters, and approaches to hybridization of algorithms. We also indicate several open problems related to the topic of the survey.

关键词： optimization metaheuristics swarm algorithm diversification intensification

来源：评论

学校读者我要写书评

暂无评论

Improving the classification performance of biological imbalanced datasets by swarm optimization algorithms

引用

JOURNAL OF SUPERCOMPUTING 2016年第10期72卷 3708-3728页

作者： Li, Jinyan Fong, Simon Mohammed, Sabah Fiaidhi, Jinan Univ Macau Dept Comp & Informat Sci Taipa Macau Peoples R China Lakehead Univ Dept Comp Sci Taipa Macau Peoples R China

Classification which is a popular supervised machine learning method has many applications in computational biology, where data samples are automatically categorized into predefined labels with the aid of data mining. Often the training samples contain very few instances of interest (e.g., medical anomalies, rare disease in a population, and unusual syndromes, etc.), but many normal instances. Such imbalanced ratio of data distributions among the target labels hampers the efficacy of classification algorithms, because the induced model has not been trained with sufficient amount of instances of the interesting label(s), but overwhelmed with ordinary training records. Traditional remedies attempt to rebalance the data distributions of the target classes, by inflating the interesting instances artificially, reducing the majority of the common instances or a combination of both. Though the fundamental concept is effective, there is no clear guideline on how to strike a balance between fabricating the rare samples and reducing the norms, with the purpose of maximizing the classification accuracy. In this paper, an optimization model using different swarm strategies (Bat-inspired algorithm and PSO) is proposed for adaptively balancing the increase/decrease of the class distribution, depending on the properties of the biological datasets. The optimization is extended for achieving the highest possible accuracy and Kappa statistics at the same time as well. The optimization model is tested on five imbalanced medical datasets, which are sourced from lung surgery logs and virtual screening of bioassay data. Computer simulation results show that the proposed optimization model outperforms other class balancing methods in medical data classification.

关键词： Imbalanced biological data Medical classification swarm algorithm Parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Prevention of Attacks on Dynamic Routing in Self-Organizing Adhoc Networks Using swarm Intelligence

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2018年第8期52卷 977-983页

作者： Kalinin, M. O. Zubkov, E. A. Suprun, A. F. Pechenkin, A. I. Peter Great St Petersburg Polytech Univ St Petersburg 195251 Russia

A technology for preventing a full range of attacks on routing in self-organizing adhoc networks (MANET, VANET/FANET/MARINET, IoT, WSN, mesh networks, M2M networks, etc.) is presented. The new technology develops the Watchdog method and the method of estimating the packet transfer coefficient (P-Secure) by implementing an ant swarm algorithm for constructing a secure route in the network, in which all nodes are agents for analyzing the security of neighboring nodes. An example is given of constructing a safe route in the VANET network using the created ant swarm algorithm.

关键词： VANET MANET black hole attack grey hole attack wormhole attack denial of service attack swarm intelligence swarm algorithm Watchdog P-Secure dynamic routing

来源：评论

学校读者我要写书评

暂无评论

Development of a technology for car's auto-parking using swarm search-based fuzzy control system

引用

INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL 2012年第1期17卷 85-97页

作者： Hanafy, Mohamed Gomaa, Mostafa M. Taher, Mohamed Wahba, Ayman M. Ain Shams Univ Fac Engn Dept Comp & Syst Engn Cairo 11517 Egypt

This paper introduces a new technique for automatic column (parallel) parking of four-wheeled cars. The intended technique is divided into two main stages. The first stage is the generation of the optimal path trajectory that the car can follow so that it can be parked in a parking lot with the minimum acceptable dimensions, after the discovery of the parking place. This stage is supported with a full parking scenario which is suitable for practical implementation. The second stage is the path tracking problem, which is solved by the design of the intended fuzzy control system. The parameters of the fuzzy controller beside the required time for parking achievement all are tuned by the search algorithm artificial fish swarm algorithm (AFSA). The performance of the involved swarm-based fuzzy controller (SBFC) is measured for solving the path tracking problem while operating on the dynamic model of a car-like robot, so that a full practical technique for car's auto parking can be completely realised. The simulation results for the path tracking problem are emphasised at the end of the paper reflecting the success of the intended auto parking control system.

关键词： automatic parking swarm algorithm fuzzy control car's dynamic model optimal path generation parking scenario path tracking problem swarm search

来源：评论

学校读者我要写书评

暂无评论

Novel Image Correction Method Based on swarm Intelligence Approach 2nd

Novel Image Correction Method Based on Swarm Intelligence Ap...

引用

22nd International Conference on Information and Software Technologies (ICIST)

作者： Wozniak, Marcin Silesian Tech Univ Inst Math Kaszubska 23 PL-44100 Gliwice Poland

ISBN: (纸本)9783319462547;9783319462530

In the article an approach toward novel method for image features correction is proposed. For the input image developed swarm intelligence technique is applied to improve brightness, contrast, sharpen presentation and improve gamma correction. The following sections present proposed model of the correction techniques with applied swarm intelligence approach. Experimental results on a set of test images are presented with a discussion of achieved improvements.

关键词： Image processing swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：